Qwen-Image 3.0 Pro API

Access Qwen-Image 3.0 Pro through GoEnhance with one endpoint for text-to-image generation and reference-guided editing. Submit a prompt, optionally add up to three image URLs, receive an img_uuid, then poll or use callbacks. GoEnhance provides independent access and is not Alibaba's official API.
Create an API Key
Unbranded studio artwork representing Qwen-Image 3.0 Pro API generation

One Endpoint for Generation and Editing

Generate from a Prompt

Omit image_list for pure text-to-image generation. Choose a supported ratio and 1K or 2K output, or let ratio: auto select the composition.
Detailed single-scene fantasy landscape representing text-to-image generation

Edit with Up to Three References

Add one to three accessible image URLs in image_list. Their order controls how the prompt refers to each source; every reference must be under 10MB.
Coherent studio still life representing reference-guided image editing
Validate the request mode, ratio, tier, and optional controls before submission.

Qwen-Image 3.0 Pro API Parameters

Required Model

Set model to qwen-image-3-pro.

Prompt

Send a required text prompt from 1 to 2000 characters.

Aspect Ratio

Choose auto or one of 13 documented ratios from 1:1 through 8:1.

Output Tier

Set image_size to 1K or 2K; the default is 2K.

Reference Images

Optionally pass one to three URL objects in image_list, each under 10MB.

Prompt Controls

Optionally add a negative prompt, a seed from 0 to 2147483647, or prompt_extend_mode. The agent mode is text-to-image only.
Cost is based on the output tier plus a per-reference-image surcharge.

Qwen-Image 3.0 Pro API Pricing

1K Output

The documented price is 2.43 tokens ($0.049) per generated 1K image.

2K Output

The documented price is 4.85 tokens ($0.097) per generated 2K image. Requests with ratio: auto are billed at this tier.

Reference Surcharge

Each reference image adds 0.19 tokens ($0.0039). Ratios 1:8 and 8:1 are limited to—and billed at—the 1K tier.

Integrate Qwen-Image 3.0 Pro in Three Steps

1

1. Build and Validate

Choose text-to-image or reference editing, write the prompt, validate ratios and image URLs, then add your authorization header.
2

2. Submit and Persist

POST the request with model: qwen-image-3-pro and save the returned img_uuid.
3

3. Handle Completion

Poll GET /api/v1/jobs/detail or accept HTTPS callback events until the task succeeds or fails, then store the output or handle the error.
Create an API Key
Support both new image generation and controlled reference-based workflows.

Qwen-Image 3.0 Pro API Use Cases

Product Visuals

Generate campaign-ready scene concepts or edit approved product references into new environments.

Ad Variations

Produce prompt-led visual directions for banners, paid media, and seasonal creative testing.

Design Prototypes

Turn written art direction into image concepts before committing to full production.

Reference-Guided Restyling

Use up to three ordered references to guide composition, subject details, or visual treatment.

Localized Campaigns

Create regional scene variations while keeping the integration contract consistent.

Content Pipelines

Connect async generation to moderation, review, storage, and publishing systems in your application.
Answers about pricing, inputs, async delivery, and Alibaba API search intent.

Qwen-Image 3.0 Pro API FAQ

How much does the Qwen-Image 3.0 Pro API cost?

GoEnhance documents 2.43 tokens ($0.049) per 1K output and 4.85 tokens ($0.097) per 2K output, plus 0.19 tokens ($0.0039) for each reference image.

Is this Alibaba's official API?

No. Qwen is associated with Alibaba, while this page describes independent API access provided by GoEnhance. It does not imply partnership or endorsement. Developers who require an Alibaba-operated API should consult Alibaba Cloud documentation.

Can the endpoint generate and edit images?

Yes. Omit image_list for text-to-image generation, or include one to three reference-image URLs for editing. The endpoint returns one generated image.

Which ratios are supported?

The documented values are auto, 1:1, 16:9, 9:16, 4:3, 3:4, 2:3, 3:2, 1:2, 2:1, 1:4, 4:1, 1:8, and 8:1.

How does prompt extension work?

The default direct mode uses the prompt directly. agent rewrites more thoroughly but is only valid for text-to-image requests without image_list.

Does the API return the image immediately?

No. A successful submission returns an img_uuid. Poll the job-detail endpoint or use callback events to retrieve the terminal result.

What happens if my callback is unavailable?

If your endpoint does not return HTTP 200, GoEnhance documents up to three callback retries with a three-second timeout per attempt. Polling remains a practical recovery path.

Build with Qwen-Image 3.0 Pro API